AI agents use create_map to create or update resources in Leaflet — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leaflet environment.
This tool creates or produces code content (HTML, CSS, JavaScript bundles) without executing it directly or modifying existing systems. The generated code is a reversible artifact that can be discarded, edited, or overwritten. It does not delete data, move money, run external commands, or have irreversible side effects.
From the tool's definition Tool generates and produces 'complete Leaflet map initialization code with HTML, CSS, and JavaScript'—creating code artifacts that are then typically saved/written to files.
Attacks that exploit this kind of access
Generate complete Leaflet map initialization code with HTML, CSS, and JavaScript. Includes tile layer setup and basic configuration. It is categorised as a Write tool in the Leaflet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Leaflet MCP server in PolicyLayer and add a rule for create_map: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Leaflet. Nothing to install.
create_map is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_map rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_map. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_map is provided by the Leaflet MCP server (philgebauer/leaflet-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →